Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Restraint of melanoma progression by cells in the local skin environment.

eLife·2026

Same author

Modulation of Oncogenic KRAS Signaling by Branched Actin-driven Cell Membrane Protrusions.

Research square·2026

Same author

Compositional and interpretable representation of histology using AI foundation models and sparse autoencoders.

bioRxiv : the preprint server for biology·2026

Same author

Modeling development of tertiary lymphoid structures in pulmonary tuberculosis by 3D profiling and trajectory analysis.

bioRxiv : the preprint server for biology·2026

Same author

Axially Swept Light-Sheet Microscopy using scattering and fluorescence contrast mechanisms.

Proceedings of SPIE--the International Society for Optical Engineering·2026

Same author

Volumetric Cyclic Immunofluorescence for 3D Spatial Profiling of Immune Structures in Human FFPE Tissue.

bioRxiv : the preprint server for biology·2026

Search research articles

Related Experiment Video

Updated: Jun 26, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

Universal consensus 3D segmentation of cells from 2D segmented stacks.

Felix Y Zhou^1,2, Zach Marin^1,2,3, Clarence Yapp^4,5

¹Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA.

Biorxiv : the Preprint Server for Biology

|May 20, 2024

Summary

This summary is machine-generated.

This study introduces u-Segment3D, a novel toolbox for 3D cell segmentation that converts 2D cell segmentations into 3D, eliminating the need for 3D training data. It offers a powerful solution for complex biological imaging challenges.

Keywords:

3D segmentation cell segmentation cellular imaging generalist algorithm image segmentation instance segmentation

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Correlative Confocal and 3D Electron Microscopy of a Specific Sensory Cell

Correlative Confocal and 3D Electron Microscopy of a Specific Sensory Cell

Published on: July 19, 2015

Related Experiment Videos

Last Updated: Jun 26, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Correlative Confocal and 3D Electron Microscopy of a Specific Sensory Cell

Correlative Confocal and 3D Electron Microscopy of a Specific Sensory Cell

Published on: July 19, 2015

Area of Science:

Microscopy and Biological Imaging
Computational Biology
Deep Learning in Biosciences

Background:

Cell segmentation is crucial for microscopy-based biological studies.
Deep learning advanced 2D cell segmentation but 3D segmentation remains challenging due to extensive annotation requirements.
Manual 3D cell annotation is prohibitive and time-consuming, even for high-contrast images.

Purpose of the Study:

To develop a theory and toolbox, u-Segment3D, for 2D-to-3D cell segmentation.
To enable 3D instance segmentation from existing 2D segmentation methods without requiring 3D training data.
To provide a generalized solution for 3D cell segmentation across diverse biological samples.

Main Methods:

Developed u-Segment3D, a toolbox for translating and enhancing 2D instance cell masks into 3D consensus instance segmentation.
The method is compatible with any 2D instance segmentation tool.
Validated on 11 real-life datasets comprising over 70,000 cells, including single cells, aggregates, and tissue.

Main Results:

u-Segment3D successfully generated 3D consensus instance segmentation from 2D segmentations without 3D training data.
The performance was evaluated across various cell types, densities, and morphologies.
Demonstrated competitive performance compared to native 3D segmentation methods, particularly in crowded and complex cellular environments.

Conclusions:

u-Segment3D provides an effective and data-efficient approach for 3D cell segmentation.
This method overcomes the limitations of manual 3D annotation, accelerating biological research.
u-Segment3D is a valuable tool for advancing 3D cell segmentation in diverse microscopy applications.